Metraipolis › archive › dc_e6bb226c4a8d
InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection — arXiv:2608.29783
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29783
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:06.053Z
- SHA-256 of the archived text
efb80f46fdbf69a11b9f9d642cebaa23538046ff5239883e608b35f2b80f4c1e- Stable URL of this page
https://metraipolis.com/documento/dc_e6bb226c4a8d
How to cite
InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection — arXiv:2608.29783 — arXiv (en), https://arxiv.org/abs/2608.29783 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6bb226c4a8d (Metraipolis archive dc_e6bb226c4a8d, sha256 efb80f46fdbf69a11b9f9d642cebaa23538046ff5239883e608b35f2b80f4c1e)
BibTeX
@misc{dce6bb226c4a8d,
title = {InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection — arXiv:2608.29783},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29783},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6bb226c4a8d; sha256 efb80f46fdbf69a11b9f9d642cebaa23538046ff5239883e608b35f2b80f4c1e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29783. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature distributions, inherently limiting generalization to unknown categories. To improve generalizability, some recent methods incorporate vision-language models (VLMs) for zero-shot detection via text prompts. However, we observe that reasoning-oriented post-training can cause anomaly discrimination to collapse, with some fine-tuned models performing worse than their base VLMs. Existing methods also provide only textual decisions or coarse boxes, without pixel-level segmentation. A more explicit detection principle comes from human inspection: anomalies are identified by comparing a query image with a defect-free reference. Inspired by this, we propose InspectorGPT, a VLM framework centered on comparative reasoning. Given a normal reference and a query image, InspectorGPT compares them to identify discrepancies and perform multiple inspection tasks with detailed reasoning. We internalize this capability through Chain-of-Thought (CoT) fine-tuning and Group Relative Policy Optimization (GRPO) with tailored, verifiable rewards. We further introduce InspectorGPT-Seg for pixel-level anomaly masks. Segmentation supervision improves anomaly discrimination but weakens semantic reasoning, while joint training fails to balance them. We therefore train the two branches separately and combine them through task-vector fusion. Extensive experiments demonstrate superior multi-dimensional performance and generalization to unseen benchmarks, validating comparative reasoning for comprehensive industrial inspection. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29783 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:48.063Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).